//----------DHTML Menu Created using AllWebMenus PRO ver 5.2-#808---------------
//C:\Users\Lila Holt\Documents\old drive\skynew\sky1.awm
var awmMenuName='menu';
var awmLibraryBuild=808;
var awmLibraryPath='/awmdata';
var awmImagesPath='/awmdata/menu';
var awmSupported=(navigator.appName + navigator.appVersion.substring(0,1)=="Netscape5" || document.all || document.layers || navigator.userAgent.indexOf('Opera')>-1 || navigator.userAgent.indexOf('Konqueror')>-1)?1:0;
if (awmAltUrl!='' && !awmSupported) window.location.replace(awmAltUrl);
if (awmSupported){
var nua=navigator.userAgent,scriptNo=(nua.indexOf('Chrome')>-1)?2:((nua.indexOf('Safari')>-1)?7:(nua.indexOf('Gecko')>-1)?2:((document.layers)?3:((nua.indexOf('Opera')>-1)?4:((nua.indexOf('Mac')>-1)?5:1))));
var mpi=document.location,xt="";
var mpa=mpi.protocol+"//"+mpi.host;
var mpi=mpi.protocol+"//"+mpi.host+mpi.pathname;
if(scriptNo==1){oBC=document.all.tags("BASE");if(oBC && oBC.length) if(oBC[0].href) mpi=oBC[0].href;}
while (mpi.search(/\\/)>-1) mpi=mpi.replace("\\","/");
mpi=mpi.substring(0,mpi.lastIndexOf("/")+1);
var e=document.getElementsByTagName("SCRIPT");
for (var i=0;i<e.length;i++){if (e[i].src){if (e[i].src.indexOf(awmMenuName+".js")!=-1){xt=e[i].src.split("/");if (xt[xt.length-1]==awmMenuName+".js"){xt=e[i].src.substring(0,e[i].src.length-awmMenuName.length-3);if (e[i].src.indexOf("://")!=-1){mpi=xt;}else{if(xt.substring(0,1)=="/")mpi=mpa+xt; else mpi+=xt;}}}}}
while (mpi.search(/\/\.\//)>-1) {mpi=mpi.replace("/./","/");}
var awmMenuPath=mpi.substring(0,mpi.length-1);
while (awmMenuPath.search("'")>-1) {awmMenuPath=awmMenuPath.replace("'","%27");}
document.write("<SCRIPT SRC='"+awmMenuPath+awmLibraryPath+"/awmlib"+scriptNo+".js'><\/SCRIPT>");
var n=null;
awmzindex=1000;
}

var awmImageName='';
var awmPosID='';
var awmSubmenusFrame='';
var awmSubmenusFrameOffset;
var awmOptimize=0;
var awmHash='HNQOUCDNOTFUSIHWAKOYCMLAEOUCDO';
var awmUseTrs=0;
var awmSepr=["0","","",""];
var awmMarg=[0,0,0,0];
function awmBuildMenu(){
if (awmSupported){
awmCreateCSS(0,1,0,n,n,n,n,n,'solid','0','#000066',0,0);
awmCreateCSS(1,2,1,'#5762A9','#D3DDF8',n,'bold 12px Tahoma',n,'none','0','#000000','3px 8px 3px 8',0);
awmCreateCSS(0,2,1,'#FFFFFF','#737FB3',n,'bold 12px Tahoma',n,'none','0','#000000','3px 8px 3px 8',0);
awmCreateCSS(0,1,0,n,n,n,n,n,'solid','3','#1D3096',0,0);
awmCreateCSS(1,2,0,'#000066','#FFFFFF',n,'bold 11px Tahoma',n,'none','0','#000000','3px 8px 3px 8',1);
awmCreateCSS(0,2,0,'#FFFFFF','#737FB3',n,'bold 11px Tahoma',n,'none','0','#000000','3px 8px 3px 8',1);
var s0=awmCreateMenu(0,0,0,0,1,0,0,0,0,10,10,0,1,0,20,1,1,n,n,100,1,0,5,0,0,-1,3,200,200,0,0,0,"0,0,0",n,n,n,n,n,n,n,n,0,0,0,0,0,0,0,0,1);
it=s0.addItem(1,2,2,"Descriptive Statistics",n,n,"","",n,n,n,n,n,0,0,2,0,0,0);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,"hideddrivetip()",100,12,1,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Measures of Central Tendency",n,n,"","MiscAndInvite01a.html","hideddrivetip()","ddrivetip('Misconception:  There are three different measures of central tendency: the mean, the median, and the mode.','white', 300)",n,"MiscAndInvite01a.html",n,0,0,2,0,0,1);
it=s1.addItem(4,5,5,"The Mean of Means",n,n,"","MiscAndInvite01b.html","hideddrivetip()","ddrivetip('Misconception:  If one large group is made up of two subgroups (e.g., males and females), and if the mean score for each subgroup is available on a variable of interest, then the mean for the full group can be computed as the mean of the two subgroup means.','white', 300)",n,"MiscAndInvite01b.html",n,0,0,2,0,0,2);
it=s1.addItem(4,5,5,"The Mode&#39;s Location",n,n,"","MiscAndInvite01c.html","hideddrivetip()","ddrivetip('Misconception:   For any distribution of scores that’s illustrated with a histogram or a smooth curve, the mode is located at the top of the tallest bar (in a histogram) or at the apex of the highest, or perhaps only, “hump” (in any picture that uses a curved line to show the distribution). ','white', 300)",n,"MiscAndInvite01c.html",n,0,0,2,0,0,3);
it=s1.addItem(4,5,5,"The Standard Deviation",n,n,"","MiscAndInvite01d.html","hideddrivetip()","ddrivetip('Misconception:   The standard deviation indicates the average (i.e., mean) numerical discrepancy between individual scores and the mean score.  ','white', 300)",n,"MiscAndInvite01d.html",n,0,0,2,0,0,4);
it=s0.addItem(1,2,2,"Reliability and Validity",n,n,"","",n,n,n,n,n,0,0,2,0,0,5);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,2,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Statistical Indices of Reliability ",n,n,"","MiscAndInvite04a.html","hideddrivetip()","ddrivetip('Misconception: Statistical indices of reliability and validity document important psychometric properties of a test. ','white', 300)",n,"MiscAndInvite04a.html",n,0,0,2,0,0,6);
it=s1.addItem(4,5,5,"Interrater Reliability",n,n,"","MiscAndInvite04b.html","hideddrivetip()","ddrivetip('Misconception: If used with the same set of data, different procedures for estimating interrater reliability yield approximately the same reliability coefficients. Therefore, it doesn’t make much of a difference which procedure is used.   ','white', 300)",n,"MiscAndInvite04b.html",n,0,0,2,0,0,7);
it=s1.addItem(4,5,5,"Cronbach&#39;s Alpha and Unidimensionality",n,n,"","MiscAndInvite04c.html","hideddrivetip()","ddrivetip('Misconception:  A high value for Cronbach’s alpha indicates that a measuring instrument’s items are all highly interrelated, thus justifying the claim that the instrument is unidimensional in what it measures.  ','white', 300)",n,"MiscAndInvite04c.html",n,0,0,2,0,0,8);
it=s1.addItem(4,5,5,"Range Restriction and Predictive Vality ",n,n,"","MiscAndInvite04d.html","hideddrivetip()","ddrivetip('Misconception:  If a product-moment correlation coefficient is used to assess predictive validity, range restriction will cause r to underestimate the strength of the relationship between the predictor and criterion variables.   ','white', 300)",n,"MiscAndInvite04d.html",n,0,0,2,0,0,9);
it=s0.addItem(1,2,2,"Estimation",n,n,"","",n,n,n,n,n,0,0,2,0,0,10);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,7,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Interpreting a Confidence Interval",n,n,"","MiscAndInvite07a.html","hideddrivetip()","ddrivetip('Misconception:  If a 95% confidence interval (CI) has been created to estimate the numerical value of a population parameter, the probability of the parameter falling somewhere between the end points of that interval is equal to .95.    ','white', 300)",n,"MiscAndInvite07a.html",n,0,0,2,0,0,11);
it=s1.addItem(4,5,5,"Overlapping Confidence Intervals",n,n,"","MiscAndInvite07b.html","hideddrivetip()","ddrivetip('Misconception:  If the 95% confidence interval (CI) that’s constructed for one sample partially overlaps the 95% CI that’s constructed for a second sample, the two samples are not significantly different from each other at alpha = .05.  CI built around one of those means overlaps the CI built around the other mean.    ','white', 300)",n,"MiscAndInvite07b.html",n,0,0,2,0,0,12);
it=s1.addItem(4,5,5,"The Mean ± the Standard Error",n,n,"","MiscAndInvite07c.html","hideddrivetip()","ddrivetip('Misconception:  If X and SE represent the sample mean and the estimated standard error of the mean, respectively, data presented in the form X ± SE is simply a 68% confidence interval. If you double SE and compute X ± 2SE, you’ll have a 95% CI.','white', 300)",n,"MiscAndInvite07c.html",n,0,0,2,0,0,13);
it=s1.addItem(4,5,5,"Confidence Intervals and Replication",n,n,"","MiscAndInvite07d.html","hideddrivetip()","ddrivetip('Misconception:  If a 95% confidence interval (CI) is constructed around a sample mean, one legitimate way to interpret the CI is to think that the chances are 95 out of 100 that the mean of a new sample of the same size drawn randomly from the same population will fall somewhere between the end points of the first sample’s CI .','white', 300)",n,"MiscAndInvite07d.html",n,0,0,2,0,0,14);
it=s0.addItem(1,2,2,"ANOVA and ANCOVA",n,n,"","",n,n,n,n,n,0,0,2,0,0,15);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,10,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Pairwise Comparisons",n,n,"","MiscAndInvite10a.html","hideddrivetip()","ddrivetip('Misconception:  If a study involves three (or more) comparison groups, one independent variable, one dependent variable, and a concern for possible differences between pairs of means, the researcher must first obtain a statistically significant F from a one-way ANOVA before having the right to make pairwise comparisons with a procedure such as Tukey’s HSD.    ','white', 300)",n,"MiscAndInvite10a.html",n,0,0,2,0,0,16);
it=s1.addItem(4,5,5,"The Cause of a Significant Interaction",n,n,"","MiscAndInvite10b.html","hideddrivetip()","ddrivetip('Misconception:  If all but one of the cell means are similar in a two-way analysis of variance (ANOVA) that produces a significant interaction, the single cell  that’s different from the others can legitimately be thought of as the reason why the interaction null hypothesis was rejected.      ','white', 300)",n,"MiscAndInvite10b.html",n,0,0,2,0,0,17);
it=s1.addItem(4,5,5,"Equal Covariate Means in ANCOVA",n,n,"","MiscAndInvite10c.html","hideddrivetip()","ddrivetip('Misconception:  If the comparison groups in a study have identical or highly similar means on a covariate variable (e.g., a pretest), there’s no reason to use an analysis of covariance (ANCOVA) to analyze the data. In this situation, data on the covariate variable should be discarded and the scores on the study’s dependent variable should be subjected to a t-test or analysis of variance (ANOVA).   ','white', 300)",n,"MiscAndInvite10c.html",n,0,0,2,0,0,18);
it=s0.addItem(1,2,2,"Distributional Shape",n,n,"","",n,n,n,n,n,0,0,2,0,0,19);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,3,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"The Shape of the Normal Curve",n,n,"","MiscAndInvite02a.html","hideddrivetip()","ddrivetip('Misconception: The normal curve is bell-shaped. When drawn, therefore, the normal curve should resemble the side view of a bell. .','white', 300)",n,"MiscAndInvite02a.html",n,0,0,2,0,0,20);
it=s1.addItem(4,5,5,"Skewed Distributions and Central Tendency",n,n,"","MiscAndInvite02b.html","hideddrivetip()","ddrivetip('Misconception:  If a set of scores forms a positively skewed distribution, the numerical values of the arithmetic mean, median, and mode will turn out such that mean > median > mode. On the other hand, if a distribution of scores is negatively skewed, mean < median < mode. ','white', 300)",n,"MiscAndInvite02b.html",n,0,0,2,0,0,21);
it=s1.addItem(4,5,5,"Standard Scores and Normality",n,n,"","MiscAndInvite02c.html","hideddrivetip()","ddrivetip('Misconception:  Standard scores, such as z¬-scores and T-scores, are normally distributed.  ','white', 300)",n,"MiscAndInvite02c.html",n,0,0,2,0,0,22);
it=s1.addItem(4,5,5,"Rectangular Distributions and Kurtosis",n,n,"","MiscAndInvite02d.html","hideddrivetip()","ddrivetip('Misconception:  Being flat, any rectangular distribution  is maximally platykurtic. ','white', 300)",n,"MiscAndInvite02d.html",n,0,0,2,0,0,23);
it=s0.addItem(1,2,2,"Probability",n,n,"","",n,n,n,n,n,0,0,2,0,0,24);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,5,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"The Binomial Distribution and N",n,n,"","MiscAndInvite05a.html","hideddrivetip()","ddrivetip('Misconception:  If a fair coin is flipped N times (with N being an even number), the potential result of “equality” (i.e., getting as many heads as tails) is more likely if N is large rather than small. ','white', 300)",n,"MiscAndInvite05a.html",n,0,0,2,0,0,25);
it=s1.addItem(4,5,5,"A Random Walk With a Perfectly Fair Coin",n,n,"","MiscAndInvite05b.html","hideddrivetip()","ddrivetip('Misconception:  If a perfectly fair coin is flipped 50 times with you betting that each flip’s outcome will be heads while a friend bets against you, then your ongoing cumulative performance—based on $1 given by the loser to the winner after each flip—will cause you to be “in the black” (i.e., with positive earnings) about as often as you are “in the red” (i.e., in debt to your friend) across the series of coin flips.    ','white', 300)",n,"MiscAndInvite05b.html",n,0,0,2,0,0,26);
it=s1.addItem(4,5,5,"Two Goats and a Car",n,n,"","MiscAndInvite05c.html","hideddrivetip()","ddrivetip('Misconception:  As a hypothetical contestant in a game show, you are shown three curtains and told that a new car is parked behind one of the curtains while a goat sits behind each of the other curtains. You then get to choose a curtain and are guaranteed that you will receive the prize behind your curtain. After making your selection, the host of the game show then opens up one of two curtains you did not select, revealing a goat. Finally, the game show host asks you whether you want to switch from the curtain you initially selected to the other unopened curtain.  	With two unopened curtains (the one you selected and the unopened curtain you did not select), intuition suggests that the chances are equal that the car is behind either of those two curtains. Therefore, it doesn’t seem make a difference whether you stay with your original selection or switch to the other unopened curtain.   ','white', 300)",n,"MiscAndInvite05c.html",n,0,0,2,0,0,27);
it=s1.addItem(4,5,5,"Identical Birthdays",n,n,"","MiscAndInvite05d.html","hideddrivetip()","ddrivetip('Misconception:  In a randomly selected group of 23 people, it’s unlikely that two or more of the individuals have the same birthday. ','white', 300)",n,"MiscAndInvite05d.html",n,0,0,2,0,0,28);
it=s1.addItem(4,5,5,"The Sum of an Infinite Number of Numbers",n,n,"","MiscAndInvite05e.html","hideddrivetip()","ddrivetip('Misconception:  The sum of an infinite number of positive numbers will be positive infinity, no matter how small the numbers are. ','white', 300)",n,"MiscAndInvite05e.html",n,0,0,2,0,0,29);
it=s1.addItem(4,5,5,"Being Diagnosed With a Rare Disease",n,n,"","MiscAndInvite05f.html","hideddrivetip()","ddrivetip('Misconception:  If someone is diagnosed as having a very rare and fatal disease, and if the procedure used to come up with this diagnosis is 99 percent accurate, then the person who’s been diagnosed has a right to feel that “the end is near.”   ','white', 300)",n,"MiscAndInvite05f.html",n,0,0,2,0,0,30);
it=s1.addItem(4,5,5,"Risk Ratios and Odds Ratios",n,n,"","MiscAndInvite05g.html","hideddrivetip()","ddrivetip('Misconception:  A risk ratio is the same thing as an odds ratio.  ','white', 300)",n,"MiscAndInvite05g.html",n,0,0,2,0,0,31);
it=s0.addItem(1,2,2,"Hypothesis Testing",n,n,"","",n,n,n,n,n,0,0,2,0,0,32);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,8,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Alpha and Type I Error Risk",n,n,"","MiscAndInvite08a.html","hideddrivetip()","ddrivetip('Misconception:  Alpha, the level of significance, defines the probability of a Type I error. For example, if   is set equal to .05, there will then necessarily be a 5 percent chance that a true null hypothesis will be rejected.','white', 300)",n,"MiscAndInvite08a.html",n,0,0,2,0,0,33);
it=s1.addItem(4,5,5,"The Null Hypothesis",n,n,"","MiscAndInvite08b.html","hideddrivetip()","ddrivetip('Misconception:  The null hypothesis is always a statement of “no difference.”  ','white', 300)",n,"MiscAndInvite08b.html",n,0,0,2,0,0,34);
it=s1.addItem(4,5,5,"Disproving Ho",n,n,"","MiscAndInvite08c.html","hideddrivetip()","ddrivetip('Misconception:  Although the null hypothesis cannot be proven true, it can be proven false. This is because science and hypothesis testing are based on the logic of falsification. If someone claims that all swans are white, confirmatory evidence (in the form of lots of white swans) cannot prove the assertion to be true. However, contradictory evidence (in the form of a single black swan) makes it clear that the claim is invalid.  Realize that sample data, by themselves, never can prove a null hypothesis to be false.  ','white', 300)",n,"MiscAndInvite08c.html",n,0,0,2,0,0,35);
it=s1.addItem(4,5,5,"The Meaning of p",n,n,"","MiscAndInvite08d.html","hideddrivetip()","ddrivetip('Misconception:  In testing a null hypothesis, the p-value based on the sample data indicates the probability that Ho is true. ','white', 300)",n,"MiscAndInvite08d.html",n,0,0,2,0,0,36);
it=s1.addItem(4,5,5,"Directionality and Tails",n,n,"","MiscAndInvite08e.html","hideddrivetip()","ddrivetip('Misconception: A non-directional alternative hypothesis always leads to a two-tailed test, whereas a directional Ha always brings about a one-tailed test.  ','white', 300)",n,"MiscAndInvite08e.html",n,0,0,2,0,0,37);
it=s1.addItem(4,5,5,"Relationshp Between Alpha &amp; Beta Errors",n,n,"","MiscAndInvite08f.html","hideddrivetip()","ddrivetip('Misconception:  There is a simple inverse relationship between the probability of a Type I error (i.e., “alpha” error) and the probability of a Type II error (i.e., “beta” error), and the level of significance should be selected to balance the risks of these two opposing kinds of inferential error.','white', 300)",n,"MiscAndInvite08f.html",n,0,0,2,0,0,38);
it=s0.addItem(1,2,2,"Significance, Power, and ES",n,n,"","",n,n,n,n,n,0,0,2,0,0,39);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,11,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Statistical vs. Practical Significance",n,n,"","MiscAndInvite11a.html","hideddrivetip()","ddrivetip('Misconception:  Statistically significant results signify strong relationships between variables or big differences between comparison groups.  ','white', 300)",n,"MiscAndInvite11a.html",n,0,0,2,0,0,40);
it=s1.addItem(4,5,5,"A Priori and Post Hoc Power",n,n,"","MiscAndInvite11b.html","hideddrivetip()","ddrivetip('Misconception:  A study’s statistical power has the same meaning regardless of whether it is estimated prior to or after the data have been gathered and analyzed.   ','white', 300)",n,"MiscAndInvite11b.html",n,0,0,2,0,0,41);
it=s1.addItem(4,5,5,"Eta Squared and Partial Eta Squared",n,n,"","MiscAndInvite11c.html","hideddrivetip()","ddrivetip('Misconception:  A study’s statistical power has the same meaning regardless of whether it is estimated prior to or after the data have been gathered and analyzed. ','white', 300)",n,"MiscAndInvite11c.html",n,0,0,2,0,0,42);
it=s0.addItem(1,2,2,"Bivariate Correlation",n,n,"","",n,n,n,n,n,0,0,2,0,0,43);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,4,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Correlation Coefficients",n,n,"","MiscAndInvite03a.html","hideddrivetip()","ddrivetip('Misconception:  Correlation coefficients range in value from –1.00 to +1.00. ','white', 300)",n,"MiscAndInvite03a.html",n,0,0,2,0,0,44);
it=s1.addItem(4,5,5,"Correlation and Causality",n,n,"","MiscAndInvite03b.html","hideddrivetip()","ddrivetip('Misconception:  The correlation between two variables, X and Y, never reveals anything about a possible causal relationship between the two variables. Simply stated: correlation ≠ cause. ','white', 300)",n,"MiscAndInvite03b.html",n,0,0,2,0,0,45);
it=s1.addItem(4,5,5,"The Effect of a Single Outlier on &nbsp;Pearson&#39;s r",n,n,"","MiscAndInvite03c.html","hideddrivetip()","ddrivetip('Misconception:  A single outlier cannot greatly influence the value of Pearson’s r, especially if N is large. ','white', 300)",n,"MiscAndInvite03c.html",n,0,0,2,0,0,46);
it=s1.addItem(4,5,5,"Relationship Strength and r",n,n,"","MiscAndInvite03d.html","hideddrivetip()","ddrivetip('Misconception:  If the data on two variables having similar distributional shapes are correlated using Pearson’s r, the resulting correlation coefficient can land anywhere on a continuum that extends from 0.00 to ±1.00; therefore, an r of +.50 (or –.50) indicates that the measured relationship is half as strong as it possibly could be. ','white', 300)",n,"MiscAndInvite03d.html",n,0,0,2,0,0,47);
it=s1.addItem(4,5,5,"The Meaning of r = 0 ",n,n,"","MiscAndInvite03e.html","hideddrivetip()","ddrivetip('Misconception:  If Pearson’s product-moment correlation, r, turns out equal to 0.00, this indicates that there is no relationship between X and Y scores used to compute that correlation coefficient.    ','white', 300)",n,"MiscAndInvite03e.html",n,0,0,2,0,0,48);
it=s0.addItem(1,2,2,"Sampling",n,n,"","",n,n,n,n,n,0,0,2,0,0,49);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,6,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"The Character of Random Samples",n,n,"","MiscAndInvite06a.html","hideddrivetip()","ddrivetip('Misconception:  If a truly random process is used to select a sample from a population, the resulting sample will turn out to be just like the population, but smaller. In other words, a random sample is like a miniature replica of the population.   ','white', 300)",n,"MiscAndInvite06a.html",n,0,0,2,0,0,50);
it=s1.addItem(4,5,5,"Random Replacements When Sampling",n,n,"","MiscAndInvite06b.html","hideddrivetip()","ddrivetip('Misconception:  A sample of individuals drawn from a larger, finite group of people deserves to be called a random sample so long as (1) everyone in the larger group has an equal chance of receiving an invitation to participate in the study and (2) random replacements are found for any of the initial invitees who decline to be involved.   ','white', 300)",n,"MiscAndInvite06b.html",n,0,0,2,0,0,51);
it=s1.addItem(4,5,5,"Precision and the Sampling Fraction",n,n,"","MiscAndInvite06c.html","hideddrivetip()","ddrivetip('Misconception: Larger populations call for larger samples. In other words, the ratio of the sample size to the population size (i.e., the sampling “fraction”) needs to be considered when deciding how large a sample should be. ','white', 300)",n,"MiscAndInvite06c.html",n,0,0,2,0,0,52);
it=s1.addItem(4,5,5,"Matched Samples",n,n,"","MiscAndInvite06d.html","hideddrivetip()","ddrivetip('Misconception:  If individuals cannot be randomly assigned to a study’s treatment and control groups, the desired condition of initial equivalence between groups can be created by using existing, pretreatment data (e.g., scores on a pretest) to create matched pairs, with one member of each pair residing in the treatment group while his/her matched pair belongs to the control group.  ','white', 300)",n,"MiscAndInvite06d.html",n,0,0,2,0,0,53);
it=s1.addItem(4,5,5,"Finite Versus Infinite Populations",n,n,"","MiscAndInvite06e.html","hideddrivetip()","ddrivetip('Misconception:  In an applied study involving inferential statistics, the population must have a specific and known (i.e., finite) size. ','white', 300)",n,"MiscAndInvite06e.html",n,0,0,2,0,0,54);
it=s0.addItem(1,2,2,"t-Tests Involving Means",n,n,"","",n,n,n,n,n,0,0,2,0,0,55);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,9,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Correlated t-Tests",n,n,"","MiscAndInvite09a.html","hideddrivetip()","ddrivetip('Misconception:  A correlated t-test focuses on the measured relationship (i.e., correlation) between two variables, with the null hypothesis being Ho: p = 0.   ','white', 300)",n,"MiscAndInvite09a.html",n,0,0,2,0,0,56);
it=s1.addItem(4,5,5,"The Difference Between Two Means If &nbsp;p &lt; .0001",n,n,"","MiscAndInvite09b.html","hideddrivetip()","ddrivetip('Misconception:  If it turns out that p < .00001 when a t-test is used to evaluate Ho: u1 = u2 , one is safe in thinking that the two sample means are radically different from each other.   ','white', 300)",n,"MiscAndInvite09b.html",n,0,0,2,0,0,57);
it=s1.addItem(4,5,5,"The Robustness of a t-Test When n1 = n2",n,n,"","MiscAndInvite09c.html","hideddrivetip()","ddrivetip('Misconception:  An independent-samples t-test is robust to violations of assumptions if the two sample sizes are equal. In other words, the t-test will function properly, even if the normality assumption or the equal variance assumption is violated (or even if both of these assumptions are violated), so long as n1 = n2. ','white', 300)",n,"MiscAndInvite09c.html",n,0,0,2,0,0,58);
it=s0.addItem(1,2,2,"Regression",n,n,"","","hideddrivetip()",n,n,n,n,0,0,2,0,0,59);
var s1=it.addSubmenu(0,0,-1,0,0,0,0,3,0,1,0,n,n,100,12,12,0,-1,1,200,200,0,0,"0,0,0",0);
it=s1.addItem(4,5,5,"Comparing Two r&#39;s; Comparing Two b&#39;s",n,n,"","MiscAndInvite12a.html","hideddrivetip()","ddrivetip('Misconception:  If two independent samples have been measured on the same two variables, a test to see if the two correlation coefficients are significantly different from each other is equivalent to a test to see if the two regression coefficients are significantly different. ','white', 300)",n,"MiscAndInvite12a.html",n,0,0,2,0,0,60);
it=s1.addItem(4,5,5,"R2",n,n,"","MiscAndInvite12b.html","hideddrivetip()","ddrivetip('Misconception:  If R2  is high, this indicates that the regression model is good in explaining variance in the dependent variable.      ','white', 300)",n,"MiscAndInvite12b.html",n,0,0,2,0,0,61);
it=s1.addItem(4,5,5,"Predictor Variables Uncorrelated with Y",n,n,"","MiscAndInvite12c.html","hideddrivetip()","ddrivetip('Misconception:  In multiple regression, an independent variable that is uncorrelated with the dependent variable ought to be left out of the model because its inclusion won’t help to make R2 larger. ','white', 300)",n,"MiscAndInvite12c.html",n,0,0,2,0,0,62);
it=s1.addItem(4,5,5,"Beta Weights",n,n,"","MiscAndInvite12d.html","hideddrivetip()","ddrivetip('Misconception:  When multiple regression is used to predict scores on a criterion variable, the worth of a particular predictor variable is indicated by that variable’s estimated beta weight (i.e., its standardized regression coefficient).  ','white', 300)",n,"MiscAndInvite12d.html",n,0,0,2,0,0,63);
s0.pm.buildMenu();
}}