Secondary Analysis under Cohort Sampling Designs Using Conditional Likelihood

<table>Sampling distributions for maximum likelihood estimates of regression coefficient <svg height="14.475" id="M407" style="vertical-align:-3.13504pt" version="1.1" viewbox="0 0 13.925 14.475" width="13.925" xmlns="http://www.w3.org/2000/svg">
<g transform="matrix(1.25,0,0,-1.25,0,14.475)">
<g transform="translate(72,-60.42)">
<text transform="matrix(1,0,0,-1,-71.95,63.6)">
<tspan style="font-size: 12.50px; " x="0" y="0">𝛽</tspan>
</text>
<text transform="matrix(1,0,0,-1,-65.79,60.47)">
<tspan style="font-size: 8.75px; " x="0" y="0">1</tspan>
</text>
</g>
</g>
</svg> from 1000 replications; NPQM model fitted to NPQM data (<svg height="14.9" id="M408" style="vertical-align:-3.2316pt" version="1.1" viewbox="0 0 177.33749 14.9" width="177.33749" xmlns="http://www.w3.org/2000/svg">
<g transform="matrix(1.25,0,0,-1.25,0,14.9)">
<g transform="translate(72,-60.08)">
<text transform="matrix(1,0,0,-1,-71.95,63.35)">
<tspan style="font-size: 12.50px; " x="0" y="0">𝑌</tspan>
</text>
<text transform="matrix(1,0,0,-1,-65.26,60.22)">
<tspan style="font-size: 8.75px; " x="0" y="0">𝑖</tspan>
</text>
<text transform="matrix(1,0,0,-1,-58.57,63.35)">
<tspan style="font-size: 12.50px; " x="0" y="0">∼</tspan>
<tspan style="font-size: 12.50px; " x="12.027886" y="0">N</tspan>
<tspan style="font-size: 12.50px; " x="21.055052" y="0">P</tspan>
<tspan style="font-size: 12.50px; " x="28.019222" y="0">Q</tspan>
<tspan style="font-size: 12.50px; " x="37.046391" y="0">M</tspan>
<tspan style="font-size: 12.50px; " x="48.161556" y="0">(</tspan>
<tspan style="font-size: 12.50px; " x="52.325054" y="0">4</tspan>
<tspan style="font-size: 12.50px; " x="58.576553" y="0">,</tspan>
<tspan style="font-size: 12.50px; " x="63.790306" y="0">2</tspan>
<tspan style="font-size: 12.50px; " x="70.041809" y="0">,</tspan>
<tspan style="font-size: 12.50px; " x="75.255554" y="0">0</tspan>
<tspan style="font-size: 12.50px; " x="81.507057" y="0">.</tspan>
<tspan style="font-size: 12.50px; " x="84.632805" y="0">1</tspan>
<tspan style="font-size: 12.50px; " x="90.884308" y="0">5</tspan>
<tspan style="font-size: 12.50px; " x="97.135803" y="0">,</tspan>
<tspan style="font-size: 12.50px; " x="102.33705" y="0">0</tspan>
<tspan style="font-size: 12.50px; " x="108.58855" y="0">.</tspan>
<tspan style="font-size: 12.50px; " x="111.7143" y="0">1</tspan>
<tspan style="font-size: 12.50px; " x="117.96581" y="0">4</tspan>
<tspan style="font-size: 12.50px; " x="124.21731" y="0">)</tspan>
</text>
</g>
</g>
</svg>).</table>

Journal of Probability and Statistics

fig6

Figure 6

Figure 6: Secondary Analysis under Cohort Sampling Designs Using Conditional Likelihood 